app/vmagent: expose /api/v1/targets page according to https://prometheus.io/docs/prometheus/latest/querying/api/#targets

This page is exposed by vmagent and by a single-node VictoriaMetrics

Updates https://github.com/VictoriaMetrics/VictoriaMetrics/issues/643

CHANGELOG.md

@@ -11,6 +11,8 @@
   See https://github.com/VictoriaMetrics/VictoriaMetrics/issues/781
 * FEATURE: vmalert: add `-dryRun` command-line option for validating the provided config files without the need to start `vmalert` service.
 * FEATURE: accept optional third argument of string type at `topk_*` and `bottomk_*` functions. This is label name for additional time series to return with the sum of time series outside top/bottom K. See [MetricsQL docs](https://victoriametrics.github.io/MetricsQL.html) for more details.
+* FEATURE: vmagent: expose `/api/v1/targets` page according to [the corresponding Prometheus API](https://prometheus.io/docs/prometheus/latest/querying/api/#targets).
+  See https://github.com/VictoriaMetrics/VictoriaMetrics/issues/643
 
 * BUGFIX: vmagent: properly handle OpenStack endpoint ending with `v3.0` such as `https://ostack.example.com:5000/v3.0`
   in the same way as Prometheus does. See https://github.com/VictoriaMetrics/VictoriaMetrics/issues/728#issuecomment-709914803

README.md

@@ -495,6 +495,7 @@ VictoriaMetrics supports the following handlers from [Prometheus querying API](h
 * [/api/v1/labels](https://prometheus.io/docs/prometheus/latest/querying/api/#getting-label-names)
 * [/api/v1/label/.../values](https://prometheus.io/docs/prometheus/latest/querying/api/#querying-label-values)
 * [/api/v1/status/tsdb](https://prometheus.io/docs/prometheus/latest/querying/api/#tsdb-stats)
+* [/api/v1/targets](https://prometheus.io/docs/prometheus/latest/querying/api/#targets) - see [these docs](#how-to-scrape-prometheus-exporters-such-as-node-exporter) for more details.
 
 These handlers can be queried from Prometheus-compatible clients such as Grafana or curl.
 

app/vmagent/README.md

@@ -211,9 +211,13 @@ either via `vmagent` itself or via Prometheus, so the exported metrics could be
 Use official [Grafana dashboard](https://grafana.com/grafana/dashboards/12683) for `vmagent` state overview.
 If you have suggestions, improvements or found a bug - feel free to open an issue on github or add review to the dashboard.
 
-`vmagent` also exports target statuses at `http://vmagent-host:8429/targets` page in plaintext format.
-`/targets` handler accepts optional `show_original_labels=1` query arg, which shows the original labels per each target
-before applying relabeling. This information may be useful for debugging target relabeling.
+`vmagent` also exports target statuses at the following handlers:
+
+* `http://vmagent-host:8429/targets`. This handler returns human-readable plaintext status for every active target.
+This page is convenient to query from command line with `wget`, `curl` or similar tools.
+It accepts optional `show_original_labels=1` query arg, which shows the original labels per each target before applying relabeling.
+This information may be useful for debugging target relabeling.
+* `http://vmagent-host:8429/api/v1/targets`. This handler returns data compatible with [the corresponding page from Prometheus API](https://prometheus.io/docs/prometheus/latest/querying/api/#targets).
 
 
 ### Troubleshooting
@@ -224,7 +228,8 @@ before applying relabeling. This information may be useful for debugging target
   since `vmagent` establishes at least a single TCP connection per each target.
 
 * When `vmagent` scrapes many unreliable targets, it can flood error log with scrape errors. These errors can be suppressed
-  by passing `-promscrape.suppressScrapeErrors` command-line flag to `vmagent`. The most recent scrape error per each target can be observed at `http://vmagent-host:8429/targets`.
+  by passing `-promscrape.suppressScrapeErrors` command-line flag to `vmagent`. The most recent scrape error per each target can be observed at `http://vmagent-host:8429/targets`
+  and `http://vmagent-host:8429/api/v1/targets`.
 
 * It is recommended to increase `-remoteWrite.queues` if `vmagent_remotewrite_pending_data_bytes` metric exported at `http://vmagent-host:8429/metrics` page constantly grows.
 

app/vmagent/main.go

@@ -211,6 +211,12 @@ func requestHandler(w http.ResponseWriter, r *http.Request) bool {
 		showOriginalLabels, _ := strconv.ParseBool(r.FormValue("show_original_labels"))
 		promscrape.WriteHumanReadableTargetsStatus(w, showOriginalLabels)
 		return true
+	case "/api/v1/targets":
+		promscrapeAPIV1TargetsRequests.Inc()
+		w.Header().Set("Content-Type", "application/json")
+		state := r.FormValue("state")
+		promscrape.WriteAPIV1Targets(w, state)
+		return true
 	case "/-/reload":
 		promscrapeConfigReloadRequests.Inc()
 		procutil.SelfSIGHUP()
@@ -242,6 +248,7 @@ var (
 	influxQueryRequests = metrics.NewCounter(`vmagent_http_requests_total{path="/query", protocol="influx"}`)
 
 	promscrapeTargetsRequests      = metrics.NewCounter(`vmagent_http_requests_total{path="/targets"}`)
+	promscrapeAPIV1TargetsRequests = metrics.NewCounter(`vmagent_http_requests_total{path="/api/v1/targets"}`)
 
 	promscrapeConfigReloadRequests = metrics.NewCounter(`vmagent_http_requests_total{path="/-/reload"}`)
 )

app/vminsert/main.go

@@ -159,6 +159,12 @@ func RequestHandler(w http.ResponseWriter, r *http.Request) bool {
 		showOriginalLabels, _ := strconv.ParseBool(r.FormValue("show_original_labels"))
 		promscrape.WriteHumanReadableTargetsStatus(w, showOriginalLabels)
 		return true
+	case "/api/v1/targets":
+		promscrapeAPIV1TargetsRequests.Inc()
+		w.Header().Set("Content-Type", "application/json")
+		state := r.FormValue("state")
+		promscrape.WriteAPIV1Targets(w, state)
+		return true
 	case "/-/reload":
 		promscrapeConfigReloadRequests.Inc()
 		procutil.SelfSIGHUP()
@@ -192,6 +198,7 @@ var (
 	influxQueryRequests = metrics.NewCounter(`vm_http_requests_total{path="/query", protocol="influx"}`)
 
 	promscrapeTargetsRequests      = metrics.NewCounter(`vm_http_requests_total{path="/targets"}`)
+	promscrapeAPIV1TargetsRequests = metrics.NewCounter(`vm_http_requests_total{path="/api/v1/targets"}`)
 
 	promscrapeConfigReloadRequests = metrics.NewCounter(`vm_http_requests_total{path="/-/reload"}`)
 

docs/Single-server-VictoriaMetrics.md

@@ -495,6 +495,7 @@ VictoriaMetrics supports the following handlers from [Prometheus querying API](h
 * [/api/v1/labels](https://prometheus.io/docs/prometheus/latest/querying/api/#getting-label-names)
 * [/api/v1/label/.../values](https://prometheus.io/docs/prometheus/latest/querying/api/#querying-label-values)
 * [/api/v1/status/tsdb](https://prometheus.io/docs/prometheus/latest/querying/api/#tsdb-stats)
+* [/api/v1/targets](https://prometheus.io/docs/prometheus/latest/querying/api/#targets) - see [these docs](#how-to-scrape-prometheus-exporters-such-as-node-exporter) for more details.
 
 These handlers can be queried from Prometheus-compatible clients such as Grafana or curl.
 

docs/vmagent.md

@@ -211,9 +211,13 @@ either via `vmagent` itself or via Prometheus, so the exported metrics could be
 Use official [Grafana dashboard](https://grafana.com/grafana/dashboards/12683) for `vmagent` state overview.
 If you have suggestions, improvements or found a bug - feel free to open an issue on github or add review to the dashboard.
 
-`vmagent` also exports target statuses at `http://vmagent-host:8429/targets` page in plaintext format.
-`/targets` handler accepts optional `show_original_labels=1` query arg, which shows the original labels per each target
-before applying relabeling. This information may be useful for debugging target relabeling.
+`vmagent` also exports target statuses at the following handlers:
+
+* `http://vmagent-host:8429/targets`. This handler returns human-readable plaintext status for every active target.
+This page is convenient to query from command line with `wget`, `curl` or similar tools.
+It accepts optional `show_original_labels=1` query arg, which shows the original labels per each target before applying relabeling.
+This information may be useful for debugging target relabeling.
+* `http://vmagent-host:8429/api/v1/targets`. This handler returns data compatible with [the corresponding page from Prometheus API](https://prometheus.io/docs/prometheus/latest/querying/api/#targets).
 
 
 ### Troubleshooting
@@ -224,7 +228,8 @@ before applying relabeling. This information may be useful for debugging target
   since `vmagent` establishes at least a single TCP connection per each target.
 
 * When `vmagent` scrapes many unreliable targets, it can flood error log with scrape errors. These errors can be suppressed
-  by passing `-promscrape.suppressScrapeErrors` command-line flag to `vmagent`. The most recent scrape error per each target can be observed at `http://vmagent-host:8429/targets`.
+  by passing `-promscrape.suppressScrapeErrors` command-line flag to `vmagent`. The most recent scrape error per each target can be observed at `http://vmagent-host:8429/targets`
+  and `http://vmagent-host:8429/api/v1/targets`.
 
 * It is recommended to increase `-remoteWrite.queues` if `vmagent_remotewrite_pending_data_bytes` metric exported at `http://vmagent-host:8429/metrics` page constantly grows.
 

lib/promscrape/config.go

@@ -642,6 +642,7 @@ func appendScrapeWork(dst []ScrapeWork, swc *scrapeWorkConfig, target string, ex
 	labels = promrelabel.RemoveMetaLabels(labels[:0], labels)
 	if len(labels) == 0 {
 		// Drop target without labels.
+		droppedTargetsMap.Register(originalLabels)
 		return dst, nil
 	}
 	// See https://www.robustperception.io/life-of-a-label
@@ -652,10 +653,12 @@ func appendScrapeWork(dst []ScrapeWork, swc *scrapeWorkConfig, target string, ex
 	addressRelabeled := promrelabel.GetLabelValueByName(labels, "__address__")
 	if len(addressRelabeled) == 0 {
 		// Drop target without scrape address.
+		droppedTargetsMap.Register(originalLabels)
 		return dst, nil
 	}
 	if strings.Contains(addressRelabeled, "/") {
 		// Drop target with '/'
+		droppedTargetsMap.Register(originalLabels)
 		return dst, nil
 	}
 	addressRelabeled = addMissingPort(schemeRelabeled, addressRelabeled)

lib/promscrape/scraper.go

@@ -284,6 +284,7 @@ func (sg *scraperGroup) update(sws []ScrapeWork) {
 					"original labels for target1: %s; original labels for target2: %s",
 					sw.ScrapeURL, sw.LabelsString(), promLabelsString(originalLabels), promLabelsString(sw.OriginalLabels))
 			}
+			droppedTargetsMap.Register(sw.OriginalLabels)
 			continue
 		}
 		swsMap[key] = sw.OriginalLabels

lib/promscrape/targetstatus.go

@@ -6,6 +6,10 @@ import (
 	"sort"
 	"sync"
 	"time"
+
+	"github.com/VictoriaMetrics/VictoriaMetrics/lib/fasttime"
+	"github.com/VictoriaMetrics/VictoriaMetrics/lib/prompbmarshal"
+	"github.com/VictoriaMetrics/VictoriaMetrics/lib/promrelabel"
 )
 
 var tsmGlobal = newTargetStatusMap()
@@ -15,6 +19,26 @@ func WriteHumanReadableTargetsStatus(w io.Writer, showOriginalLabels bool) {
 	tsmGlobal.WriteHumanReadable(w, showOriginalLabels)
 }
 
+// WriteAPIV1Targets writes /api/v1/targets to w according to https://prometheus.io/docs/prometheus/latest/querying/api/#targets
+func WriteAPIV1Targets(w io.Writer, state string) {
+	if state == "" {
+		state = "any"
+	}
+	fmt.Fprintf(w, `{"status":"success","data":{"activeTargets":`)
+	if state == "active" || state == "any" {
+		tsmGlobal.WriteActiveTargetsJSON(w)
+	} else {
+		fmt.Fprintf(w, `[]`)
+	}
+	fmt.Fprintf(w, `,"droppedTargets":`)
+	if state == "dropped" || state == "any" {
+		droppedTargetsMap.WriteDroppedTargetsJSON(w)
+	} else {
+		fmt.Fprintf(w, `[]`)
+	}
+	fmt.Fprintf(w, `}}`)
+}
+
 type targetStatusMap struct {
 	mu sync.Mutex
 	m  map[uint64]targetStatus
@@ -73,6 +97,66 @@ func (tsm *targetStatusMap) StatusByGroup(group string, up bool) int {
 	return count
 }
 
+// WriteActiveTargetsJSON writes `activeTargets` contents to w according to https://prometheus.io/docs/prometheus/latest/querying/api/#targets
+func (tsm *targetStatusMap) WriteActiveTargetsJSON(w io.Writer) {
+	tsm.mu.Lock()
+	type keyStatus struct {
+		key string
+		st  targetStatus
+	}
+	kss := make([]keyStatus, 0, len(tsm.m))
+	for _, st := range tsm.m {
+		key := promLabelsString(st.sw.OriginalLabels)
+		kss = append(kss, keyStatus{
+			key: key,
+			st:  st,
+		})
+	}
+	tsm.mu.Unlock()
+
+	sort.Slice(kss, func(i, j int) bool {
+		return kss[i].key < kss[j].key
+	})
+	fmt.Fprintf(w, `[`)
+	for i, ks := range kss {
+		st := ks.st
+		fmt.Fprintf(w, `{"discoveredLabels":`)
+		writeLabelsJSON(w, st.sw.OriginalLabels)
+		fmt.Fprintf(w, `,"labels":`)
+		labelsFinalized := promrelabel.FinalizeLabels(nil, st.sw.Labels)
+		writeLabelsJSON(w, labelsFinalized)
+		fmt.Fprintf(w, `,"scrapePool":%q`, st.sw.Job())
+		fmt.Fprintf(w, `,"scrapeUrl":%q`, st.sw.ScrapeURL)
+		errMsg := ""
+		if st.err != nil {
+			errMsg = st.err.Error()
+		}
+		fmt.Fprintf(w, `,"lastError":%q`, errMsg)
+		fmt.Fprintf(w, `,"lastScrape":%q`, time.Unix(st.scrapeTime/1000, (st.scrapeTime%1000)*1e6).Format(time.RFC3339Nano))
+		fmt.Fprintf(w, `,"lastScrapeDuration":%g`, (time.Millisecond * time.Duration(st.scrapeDuration)).Seconds())
+		state := "up"
+		if !st.up {
+			state = "down"
+		}
+		fmt.Fprintf(w, `,"health":%q}`, state)
+		if i+1 < len(kss) {
+			fmt.Fprintf(w, `,`)
+		}
+	}
+	fmt.Fprintf(w, `]`)
+}
+
+func writeLabelsJSON(w io.Writer, labels []prompbmarshal.Label) {
+	fmt.Fprintf(w, `{`)
+	for i, label := range labels {
+		fmt.Fprintf(w, "%q:%q", label.Name, label.Value)
+		if i+1 < len(labels) {
+			fmt.Fprintf(w, `,`)
+		}
+	}
+	fmt.Fprintf(w, `}`)
+}
+
 func (tsm *targetStatusMap) WriteHumanReadable(w io.Writer, showOriginalLabels bool) {
 	byJob := make(map[string][]targetStatus)
 	tsm.mu.Lock()
@@ -143,3 +227,69 @@ type targetStatus struct {
 func (st *targetStatus) getDurationFromLastScrape() time.Duration {
 	return time.Since(time.Unix(st.scrapeTime/1000, (st.scrapeTime%1000)*1e6))
 }
+
+type droppedTargets struct {
+	mu              sync.Mutex
+	m               map[string]droppedTarget
+	lastCleanupTime uint64
+}
+
+type droppedTarget struct {
+	originalLabels []prompbmarshal.Label
+	deadline       uint64
+}
+
+func (dt *droppedTargets) Register(originalLabels []prompbmarshal.Label) {
+	key := promLabelsString(originalLabels)
+	currentTime := fasttime.UnixTimestamp()
+	dt.mu.Lock()
+	dt.m[key] = droppedTarget{
+		originalLabels: originalLabels,
+		deadline:       currentTime + 10*60,
+	}
+	if currentTime-dt.lastCleanupTime > 60 {
+		for k, v := range dt.m {
+			if currentTime > v.deadline {
+				delete(dt.m, k)
+			}
+		}
+		dt.lastCleanupTime = currentTime
+	}
+	dt.mu.Unlock()
+}
+
+// WriteDroppedTargetsJSON writes `droppedTargets` contents to w according to https://prometheus.io/docs/prometheus/latest/querying/api/#targets
+func (dt *droppedTargets) WriteDroppedTargetsJSON(w io.Writer) {
+	dt.mu.Lock()
+	type keyStatus struct {
+		key            string
+		originalLabels []prompbmarshal.Label
+	}
+	kss := make([]keyStatus, 0, len(dt.m))
+	for _, v := range dt.m {
+		key := promLabelsString(v.originalLabels)
+		kss = append(kss, keyStatus{
+			key:            key,
+			originalLabels: v.originalLabels,
+		})
+	}
+	dt.mu.Unlock()
+
+	sort.Slice(kss, func(i, j int) bool {
+		return kss[i].key < kss[j].key
+	})
+	fmt.Fprintf(w, `[`)
+	for i, ks := range kss {
+		fmt.Fprintf(w, `{"discoveredLabels":`)
+		writeLabelsJSON(w, ks.originalLabels)
+		fmt.Fprintf(w, `}`)
+		if i+1 < len(kss) {
+			fmt.Fprintf(w, `,`)
+		}
+	}
+	fmt.Fprintf(w, `]`)
+}
+
+var droppedTargetsMap = &droppedTargets{
+	m: make(map[string]droppedTarget),
+}